Faculty Bibliography

BACKGROUND:Detection of rotator cuff tears, a common cause of shoulder disability, can be time-consuming and subject to reader variability. Deep learning (DL) has the potential to increase radiologist accuracy and consistency. PURPOSE:The aim of this study was to develop a prototype DL model for detection and classification of rotator cuff tears on shoulder magnetic resonance imaging into no tear, partial-thickness tear, or full-thickness tear. MATERIALS AND METHODS:This Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included a total of 11,925 noncontrast shoulder magnetic resonance imaging scans from 2 institutions, with 11,405 for development and 520 dedicated for final testing. A DL ensemble algorithm was developed that used 4 series as input from each examination: fluid-sensitive sequences in 3 planes and a sagittal oblique T1-weighted sequence. Radiology reports served as ground truth for training with categories of no tear, partial tear, or full-thickness tear. A multireader study was conducted for the test set ground truth, which was determined by the majority vote of 3 readers per case. The ensemble comprised 4 parallel 3D ResNet50 convolutional neural network architectures trained via transfer learning and then adapted to the targeted domain. The final tear-type prediction was determined as the class with the highest probability, after averaging the class probabilities of the 4 individual models. RESULTS:The AUC overall for supraspinatus, infraspinatus, and subscapularis tendon tears was 0.93, 0.89, and 0.90, respectively. The model performed best for full-thickness supraspinatus, infraspinatus, and subscapularis tears with AUCs of 0.98, 0.99, and 0.95, respectively. Multisequence input demonstrated higher AUCs than single-sequence input for infraspinatus and subscapularis tendon tears, whereas coronal oblique fluid-sensitive and multisequence input showed similar AUCs for supraspinatus tendon tears. Model accuracy for tear types and overall accuracy were similar to that of the clinical readers. CONCLUSIONS:Deep learning diagnosis of rotator cuff tears is feasible with excellent diagnostic performance, particularly for full-thickness tears, with model accuracy similar to subspecialty-trained musculoskeletal radiologists.

Acute ankle sprains are common sports injuries. MRI is the most accurate test for assessing the integrity and severity of ligament injuries in acute ankle sprains. However, MRI may not detect syndesmotic and hindfoot instability, and many ankle sprains are treated conservatively, questioning the value of MRI. In our practice, MRI adds value in confirming the absence or presence of ankle sprain-associated hindfoot and midfoot injuries, especially when clinical examinations are challenging, radiographs are inconclusive, and subtle instability is suspected. This article reviews and illustrates the MRI appearances of the spectrum of ankle sprains and associated hindfoot and midfoot injuries.

Foot and ankle injuries are common musculoskeletal disorders. In the acute setting, ligamentous injuries are most common, whereas fractures, osseous avulsion injuries, tendon and retinaculum tears, and osteochondral injuries are less common. The most common chronic and overuse injuries include osteochondral and articular cartilage defects, tendinopathies, stress fractures, impingement syndromes, and neuropathies. Common forefoot conditions include traumatic and stress fractures, metatarsophalangeal and plantar plate injuries and degenerations, intermittent bursitis, and perineural fibrosis. Ultrasonography is well-suited for evaluating superficial tendons, ligaments, and muscles. MR imaging is best for deeper-located soft tissue structures, articular cartilage, and cancellous bone.

Elbow pain is very common and can be due to many pathologic conditions. After radiographs are obtained, advanced imaging is often necessary. Both ultrasonography and MR imaging can be used to evaluate the many important soft-tissue structures of the elbow, with each modality having advantages and disadvantages in certain clinical scenarios. Imaging findings between the two modalities often correlate. It is important for musculoskeletal radiologists to understand normal elbow anatomy and how best to use ultrasonography and MR imaging to evaluate elbow pain. In this way, radiologists can provide expert guidance to referring clinicians and best guide patient management.

Evaluation of soft-tissue masses has become a common clinical practice indication for imaging with both ultrasound and MR imaging. We illustrate the ultrasonography and MR imaging appearances of soft-tissue masses based on the various categories, updates, and reclassifications of the 2020 World Health Organization classification.

Acute knee injury ranges among the most common joint injuries in professional and recreational athletes. Radiographs can detect joint effusion, fractures, deformities, and malalignment; however, MR imaging is most accurate for radiographically occult fractures, chondral injury, and soft tissue injuries. Using a structured checklist approach for systematic MR imaging evaluation and reporting, this article reviews the MR imaging appearances of the spectrum of traumatic knee injuries, including osteochondral injuries, cruciate ligament tears, meniscus tears and ramp lesions, anterolateral complex and collateral ligament injuries, patellofemoral translation, extensor mechanism tears, and nerve and vascular injuries.

Decades of technical innovations have propelled musculoskeletal radiology through an astonishing evolution. New artificial intelligence and deep learning methods capitalize on many past innovations in magnetic resonance imaging (MRI) to reach unprecedented speed, image quality, and new contrasts. Similarly exciting developments in computed tomography (CT) include clinically applicable molecular specificity and substantially improved spatial resolution of musculoskeletal structures and diseases. This special issue of Investigative Radiology comprises a collection of expert summaries and reviews on the most impactful innovations and cutting-edge topics in musculoskeletal radiology, including radiomics and deep learning methods for musculoskeletal disease detection, high-resolution MR neurography, deep learning-driven ultra-fast musculoskeletal MRI, MRI-based synthetic CT, quantitative MRI, modern low-field MRI, 7.0 T MRI, dual-energy CT, cone beam CT, kinematic CT, and synthetic contrast generation in musculoskeletal MRI.

Magnetic resonance imaging (MRI) is the keystone of modern musculoskeletal imaging; however, long pulse sequence acquisition times may restrict patient tolerability and access. Advances in MRI scanners, coil technology, and innovative pulse sequence acceleration methods enable 4-fold turbo spin echo pulse sequence acceleration in clinical practice; however, at this speed, conventional image reconstruction approaches the signal-to-noise limits of temporal, spatial, and contrast resolution. Novel deep learning image reconstruction methods can minimize signal-to-noise interdependencies to better advantage than conventional image reconstruction, leading to unparalleled gains in image speed and quality when combined with parallel imaging and simultaneous multislice acquisition. The enormous potential of deep learning-based image reconstruction promises to facilitate the 10-fold acceleration of the turbo spin echo pulse sequence, equating to a total acquisition time of 2-3 minutes for entire MRI examinations of joints without sacrificing spatial resolution or image quality. Current investigations aim for a better understanding of stability and failure modes of image reconstruction networks, validation of network reconstruction performance with external data sets, determination of diagnostic performances with independent reference standards, establishing generalizability to other centers, scanners, field strengths, coils, and anatomy, and building publicly available benchmark data sets to compare methods and foster innovation and collaboration between the clinical and image processing community. In this article, we review basic concepts of deep learning-based acquisition and image reconstruction techniques for accelerating and improving the quality of musculoskeletal MRI, commercially available and developing deep learning-based MRI solutions, superresolution, denoising, generative adversarial networks, and combined strategies for deep learning-driven ultra-fast superresolution musculoskeletal MRI. This article aims to equip radiologists and imaging scientists with the necessary practical knowledge and enthusiasm to meet this exciting new era of musculoskeletal MRI.